mlsanityData to 14 Oct 2026

FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting

arXiv 2605.00177 ↗First posted 30 Apr 2026cs.GR cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

We consider the problem of synthesizing photorealistic, physically plausible combustion effects in in-the-wild 3D scenes. Traditional CFD and graphics pipelines can produce realistic fire effects but rely on handcrafted geometry, expert-tuned parameters, and labor-intensive workflows, limiting their scalability to the real world. Recent scene modeling advances like 3D Gaussian Splatting (3DGS) enable high-fidelity real-world scene reconstruction, yet lack physical grounding for combustion. To bridge this gap, we propose FieryGS, a physically-based framework that integrates physically-accurate and user-controllable combustion simulation and rendering within the 3DGS pipeline, enabling realistic fire synthesis for real scenes. Our approach tightly couples three key modules: (1) multimodal large-language-model-based physical material reasoning, (2) efficient volumetric combustion simulation, and (3) a unified renderer for fire and 3DGS. By unifying reconstruction, physical reasoning, simulation, and rendering, FieryGS removes manual tuning and automatically generates realistic, controllable fire dynamics consistent with scene geometry and materials. Our framework supports complex combustion phenomena -- including flame propagation, smoke dispersion, and surface carbonization -- with precise user control over fire intensity, airflow, ignition location and other combustion parameters. Evaluated on diverse indoor and outdoor scenes, FieryGS outperforms all comparative baselines in visual realism, physical fidelity, and controllability. Project page can be found at https://pku-vcl-geometry.github.io/FieryGS/.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

33 of 63 references.

References · 33

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2023Segment Anythingcited by 8,234
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2024GPT-4o System Cardcited by 4,588
  7. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,708
  8. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  9. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  11. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
  12. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
21 more
  1. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
  2. 2024PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generationcited by 191
  3. 2024PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generationcited by 174
  4. 2023Segment Any 3D Gaussianscited by 161
  5. 2023PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identificationcited by 154
  6. 2024One-Step Image Translation with Text-to-Image Modelscited by 116
  7. 2024GARField: Group Anything with Radiance Fieldscited by 109
  8. 2024Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussianscited by 97
  9. 2024Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusioncited by 80
  10. 2025OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generationcited by 69
  11. 2024GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulationcited by 49
  12. 2024Physical Property Understanding from Language-Embedded Feature Fieldscited by 48
  13. 2022ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Fieldcited by 37
  14. 2024Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Renderingcited by 37
  15. 2024PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulationcited by 36
  16. 2024Neural Material Adaptor for Visual Grounding of Intrinsic Dynamicscited by 32
  17. 2024AutoVFX: Physically Realistic Video Editing from Natural Language Instructionscited by 27
  18. 2025PUGS: Zero-shot Physical Understanding with Gaussian Splattingcited by 24
  19. 2024GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMscited by 23
  20. 2025RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splattingcited by 13
  21. 2024FlameForge: Combustion of Generalized Wooden Structurescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.